Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge

• URL: http://arxiv.org/abs/2410.07379v1
• Date: Wed, 9 Oct 2024 18:55:28 GMT
• Title: Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge
• Authors: Yi Zhu, Chirag Goel, Surya Koppisetti, Trang Tran, Ankur Kumar, Gaurav Bharaj,
• Abstract summary: ASVspoof challenge has become one of the benchmarks to evaluate the generalizability and robustness of detection models. We present Reality Defender's submission to the ASVspoof5 challenge, highlighting a novel pretraining strategy. Our system SLIM learns the style-linguistics dependency embeddings from various types of bonafide speech using self-supervised contrastive learning.
• Score: 13.54987267358107
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio deepfake detection is crucial to combat the malicious use of AI-synthesized speech. Among many efforts undertaken by the community, the ASVspoof challenge has become one of the benchmarks to evaluate the generalizability and robustness of detection models. In this paper, we present Reality Defender's submission to the ASVspoof5 challenge, highlighting a novel pretraining strategy which significantly improves generalizability while maintaining low computational cost during training. Our system SLIM learns the style-linguistics dependency embeddings from various types of bonafide speech using self-supervised contrastive learning. The learned embeddings help to discriminate spoof from bonafide speech by focusing on the relationship between the style and linguistics aspects. We evaluated our system on ASVspoof5, ASV2019, and In-the-wild. Our submission achieved minDCF of 0.1499 and EER of 5.5% on ASVspoof5 Track 1, and EER of 7.4% and 10.8% on ASV2019 and In-the-wild respectively.

Related papers

• Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples [33.445126880876415]
  We propose a reliable and robust spoofing detection system to filter out spoofing attacks instead of having them reach the automatic speaker verification system. A weighted additive angular margin loss is proposed to address the data imbalance issue, and different margins has been assigned to improve generalization to unseen spoofing attacks. We craft adversarial examples by adding imperceptible perturbations to spoofing speech as a data augmentation strategy, then we use an auxiliary batch normalization to guarantee that corresponding normalization statistics are performed exclusively on the adversarial examples.
  arXiv  Detail & Related papers  (2024-08-23T19:26:54Z)
• ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale [59.25180900687571]
  ASVspoof 5 is the fifth edition in a series of challenges that promote the study of speech spoofing and deepfake attacks. We describe the two challenge tracks, the new database, the evaluation metrics, and the evaluation platform, and present a summary of the results.
  arXiv  Detail & Related papers  (2024-08-16T13:37:20Z)
• Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge [21.655127750485097]
  We introduce Frequency Mask, a data augmentation method that masks specific frequency bands to improve CM. Our experiments achieved a minDCF of 0.0158 and an EER of 0.55% on the ASVspoof 5 Track 1 evaluation progress set.
  arXiv  Detail & Related papers  (2024-08-13T14:15:15Z)
• Generalizing Speaker Verification for Spoof Awareness in the Embedding Space [30.094557217931563]
  ASV systems can be spoofed using various types of adversaries. We propose a novel yet simple backend classifier based on deep neural networks. Experiments are conducted on the ASVspoof 2019 logical access dataset.
  arXiv  Detail & Related papers  (2024-01-20T07:30:22Z)
• Towards single integrated spoofing-aware speaker verification embeddings [63.42889348690095]
  This study aims to develop a single integrated spoofing-aware speaker verification embeddings. We analyze that the inferior performance of single SASV embeddings comes from insufficient amount of training data. Experiments show dramatic improvements, achieving a SASV-EER of 1.06% on the evaluation protocol of the SASV2022 challenge.
  arXiv  Detail & Related papers  (2023-05-30T14:15:39Z)
• Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE [93.98660272309974]
  This report briefly describes our submission Vega v1 on the General Language Understanding Evaluation leaderboard. GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference. With our optimized pretraining and fine-tuning strategies, our 1.3 billion model sets new state-of-the-art on 4/9 tasks, achieving the best average score of 91.3.
  arXiv  Detail & Related papers  (2023-02-18T09:26:35Z)
• Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning [95.60856995067083]
  This work is among the first to perform adversarial defense for ASV without knowing the specific attack algorithms. We propose to perform adversarial defense from two perspectives: 1) adversarial perturbation purification and 2) adversarial perturbation detection. Experimental results show that our detection module effectively shields the ASV by detecting adversarial samples with an accuracy of around 80%.
  arXiv  Detail & Related papers  (2021-06-01T07:10:54Z)
• Adversarial defense for automatic speaker verification by cascaded self-supervised learning models [101.42920161993455]
  More and more malicious attackers attempt to launch adversarial attacks at automatic speaker verification (ASV) systems. We propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks.
  arXiv  Detail & Related papers  (2021-02-14T01:56:43Z)
• Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement [102.48582597586233]
  We present a U-Net based attention model, U-Net$_At$, to enhance adversarial speech signals. We conduct experiments on the automatic speech recognition (ASR) task with adversarial audio attacks.
  arXiv  Detail & Related papers  (2020-03-31T02:16:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.